[Bug]: The ports on which the serving function runs and the container redirection do not match

[Nikitala0014]

MLRun Version checks

• I have checked that this issue has not already been reported.

• I have confirmed this bug exists on the latest version of MLRun CE.

Reproducible Example

serving_fn.invoke(path=model_inference_path, body={"inputs": [sample_id]})

Issue Description

After deployment this function returns the following error: Max retries exceeded. I use a stable address. Therefore, there is a connection to the container.
The problem is that container port to 8080 inside: c3422c55e73d nuclio/processor-stock-prediction-chris-stocks-serving:latest "processor" 20 seconds ago Up 19 seconds (healthy) 0.0.0.0:32810->8080/tcp, :::32810->8080/tcp nuclio-nuclio-stock-prediction-chris-stocks-serving
But the service inside container working on 8082

Expected Behavior

Failed to establish a new connection: [Errno 111] Connection refused

Installation OS

Linux

Installation Method

Docker

Python Version

3.9

MLRun Version

1.4.0

Additional Information

No response

[Nikitala0014]

Inside the container

[Nikitala0014]

As far as I understand from the code, all the logic happens in the mlrun container, and the code simply calls the build method "build/function" with this arguments.
This means that nothing I can do from the project code to resolve this. The problem is in some initial configuration